EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Attention-Residual Convolutional Network for Real-Time Seizure Classification on Edge Devices

Peter A Akor iD, Godwin Enemali iD, Usman Muhammad, Rajiv Ranjan Singh iD, Hadi Larijani iD

Sensors · 10.11.2025 · 25 (22) · 6855

DOI: 10.3390/s25226855 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.11.2025. Verfasst von Peter A Akor und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Science and Engineering, Glasgow Caledonian University, Glasgow G4 0BA, UK. Hauptthemen laut MEDLINE: Seizures, Electroencephalography, Neural Networks, Computer. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Epilepsy affects over 50 million people globally, with accurate seizure type classification directly influencing treatment selection as different seizure types respond to specific antiepileptic medications. Manual electroencephalogram (EEG) interpretation remains time-intensive and requires specialized expertise, creating clinical workflow bottlenecks. This work presents EEG-ARCNet, an attention-residual convolutional network integrating residual connections with channel attention mechanisms to extract discriminative temporal and spectral features from multi-channel EEG recordings. The model combines nine statistical temporal features with five frequency-band power measures through Welch’s spectral decomposition, processed through attention-enhanced convolutional pathways. Evaluated on the Temple University Hospital Seizure Corpus, EEG-ARCNet achieved 99.65% accuracy with 99.59% macro-averaged F1-score across five seizure types (absence, focal non-specific, simple partial, tonic-clonic, and tonic). To validate practical deployment, the model was implemented on Raspberry Pi 4, achieving a 2.06 ms average inference time per 10 s segment with 35.4% CPU utilization and 499.4 MB memory consumption. The combination of high classification accuracy and efficient edge deployment demonstrates technical feasibility for resource-constrained seizure-monitoring applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SeizuresElectroencephalographyNeural Networks, ComputerHumansAlgorithmsSignal Processing, Computer-AssistedEpilepsy

Stichwörter der Autor:innen

EEG analysisRaspberry Piattention mechanismedge computingepilepsy monitoringresidual networkseizure classification

Autor:innen und Institutionen

  • School of Science and Engineering, Glasgow Caledonian University, Glasgow G4 0BA, UK.

ORCID-Profile: Peter A Akor, Godwin Enemali, Rajiv Ranjan Singh, Hadi Larijani

Zitieren

APA

Akor, P. A., Enemali, G., Muhammad, U., Singh, R. R., & Larijani, H. (2025). An Attention-Residual Convolutional Network for Real-Time Seizure Classification on Edge Devices. Sensors, 25(22), 6855. https://doi.org/10.3390/s25226855

Vancouver

Akor PA, Enemali G, Muhammad U, Singh RR, Larijani H. An Attention-Residual Convolutional Network for Real-Time Seizure Classification on Edge Devices. Sensors. 2025;25(22):6855. doi:10.3390/s25226855

BibTeX
@article{Akor2025,
  author = {Akor, Peter A and Enemali, Godwin and Muhammad, Usman and Singh, Rajiv Ranjan and Larijani, Hadi},
  title = {An Attention-Residual Convolutional Network for Real-Time Seizure Classification on Edge Devices},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {22},
  pages = {6855},
  doi = {10.3390/s25226855}
}
Kostenlos starten →